Related papers: Corrigendum to "Random grid-based visual secret sh…
Stein discrepancies (SDs) monitor convergence and non-convergence in approximate inference when exact integration and sampling are intractable. However, the computation of a Stein discrepancy can be prohibitive if the Stein operator - often…
In this first of two papers, we explain in detail the simplest example of a broader set of relations between apparently very different theories. Our example relates $\mathfrak{su}(2)$ $\mathcal{N}=4$ super Yang-Mills (SYM) to a theory we…
Most of optical gravitational lenses recently discovered in the Sloan Digital Sky Survey Quasar Lens Search (SQLS) have two-images rather than four-images, in marked contrast to radio lenses for which the fraction of four-image lenses (quad…
Learning-based multi-view stereo (MVS) methods have demonstrated promising results. However, very few existing networks explicitly take the pixel-wise visibility into consideration, resulting in erroneous cost aggregation from occluded…
[Abridged] We present reliable multiwavelength identifications and high-quality photometric redshifts for the 462 X-ray sources in the ~2 Ms Chandra Deep Field-South. Source identifications are carried out using deep optical-to-radio…
Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive…
Neural networks (NN) for single-view 3D reconstruction (SVR) have gained in popularity. Recent work points out that for SVR, most cutting-edge NNs have limited performance on reconstructing unseen objects because they rely primarily on…
Performance of concatenated multilevel coding with probabilistic shaping (PS) and Voronoi constellations (VCs) is analysed over AWGN channel. Numerical results show that VCs provide up to 1.3 dB SNR gains over PS-QAM with CCDM blocklength…
We present a new cluster-finding algorithm based on a combination of the Voronoi Tessellation and Friends-Of-Friends methods. The algorithm utilises probability distribution functions derived from a photometric redshift analysis. We test…
In the paper we apply graph vertex coloring for verification of secret shares. We start from showing how to convert any graph into the number and vice versa. Next, theoretical result concerning properties of n-colorable graphs is stated and…
This paper addresses the challenges in representation learning of 3D shape features by investigating state-of-the-art backbones paired with both contrastive supervised and self-supervised learning objectives. Computer vision methods…
Sign stochastic gradient descent (signSGD) is a communication-efficient method that transmits only the sign of stochastic gradients for parameter updating. Existing literature has demonstrated that signSGD can achieve a convergence rate of…
We consider travel time tomography problems involving detection of high contrast, discrete high velocity structures. This results in a discrete nonlinear inverse problem, for which traditional grid-based models and iterative linearized…
Increasing deployment of photovoltaic (PV) plants requires methods for automatic detection of faulty PV modules in modalities, such as infrared (IR) images. Recently, deep learning has become popular for this. However, related works…
Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five…
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although…
Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficult to interpret, and there are several competing techniques…
The contrast of granulation is an important quantity characterizing solar surface convection. We compare the intensity contrast at 630 nm, observed using the Spectro-Polarimeter (SP) aboard the Hinode satellite, with the 3D radiative MHD…
Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…
Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…